Significance ranking of parameters impacting construction labour productivity

Moselhi, O and Khan, Z (2012) Significance ranking of parameters impacting construction labour productivity. Construction Innovation, 12(3), pp. 272-296. ISSN 1471-4175

Abstract

Purpose - Construction labour productivity is often influenced by variations in work conditions and management effectiveness. It is substantially important to understand the nature and extent to which individual parameters affect productivity. The purpose of this paper is to focus on providing insight on parameters that affect daily job-site labour productivity by investigating their relative significance and influence on work output. Design/methodology/ approach - The methodology is based on the illustration and use of three different data analysis techniques to rank parameters that affect a certain process. These techniques include Fuzzy Subtractive Clustering, Neural Network Modelling and Stepwise Variable Selection Procedure. The first one belongs to inferential statistics, while the other two are artificial intelligence based techniques. The collection of field information, spanning over a time period of ten months, comprised of daily real time observations of job-site operations, work progress information collected from project managers and supervisors by using customized forms, and daily weather condition recorded through internet sources. Nine parameters are considered in the study presented in this paper. The data on these parameters is examined and their relative influence and contribution in productivity estimates are assessed. The approach was to consider a limited set of parameters relating to daily job-site productivity. The methodology presented in this paper provides insight on the relative impact of parameters, affecting labour productivity on short term or daily basis. The results based on each of the three methods are analyzed and transformed into a final ranking of parameters. Findings - The three most important parameters are identified in the same order by the fuzzy logic and neural networks methods. Regression analysis, however, provided somewhat different results. Originality/value - This research investigates the contribution of a set of parameters towards the variations in daily job-site labour productivity. For practitioners such as site engineers, this is of practical importance for making daily work plans. On the other hand, the structured approach presented to perform significance ranking of parameters relevant to an engineering process, may also be of interest to other researchers and practitioners.

Item Type: Article
Uncontrolled Keywords: construction; construction industry; fuzzy logic; labour productivity; neural network; regression; variable selection
Index terms: practitioner, methodology, variation, weather, data analysis, management effectiveness, neural network, site operation, labour productivity, construction labour, real time, artificial intelligence, regression analysis, supervisor, statistics, clustering, construction industry, internet, modelling, estimate, fuzzy logic, project manager, productivity, engineer
Subjects: data science, artificial intelligence, data analysis and analytics, analytical methods, financial and cost management, operations management, computing systems, practitioner, profession, air quality, mathematical modelling, industry analysis, statistical analysis, project controls, contractual condition, management, performance measurement, research methods
Topics: Digital Applications, Quality Management, Contract Administration, Time Control, Site Management, Cost Management, Business Strategy, Engineering Principles, Research Practice, Roles and Professions, Sustainability
Descriptive scope: 4 PCTA

N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here